Browserbase MCP server for AI agents

The Browserbase MCP Server provides cloud browser automation capabilities using Browserbase and Stagehand, enabling LLMs to interact with web pages, take screenshots, extract information, and perform automated actions with atomic precision. It integrates with the Model Context Protocol (MCP) to connect AI models with web browsing capabilities.

Installation Options

Quick Setup with Remote Hosted Server (Recommended)

The easiest way to use Browserbase MCP is through the remote hosted URL:

Go to smithery.ai to generate your remote hosted URL
Enter your API keys and configuration
Add the server to your MCP configuration:

For clients supporting SHTTP:

{
  "mcpServers": {
    "browserbase": {
      "url": "your-smithery-url.com"
    }
  }
}

For clients that don't support SHTTP:

{
  "mcpServers": {
    "browserbase": {
      "command": "npx",
      "args": ["mcp-remote", "your-smithery-url.com"]
    }
  }
}

Using NPM

To install via NPM:

{
  "mcpServers": {
    "browserbase": {
      "command": "npx",
      "args": ["@browserbasehq/mcp-server-browserbase"],
      "env": {
        "BROWSERBASE_API_KEY": "",
        "BROWSERBASE_PROJECT_ID": "",
        "GEMINI_API_KEY": ""
      }
    }
  }
}

Local Installation

For a fully local installation:

Clone the repository:

git clone https://github.com/browserbase/mcp-server-browserbase.git
cd mcp-server-browserbase

Install dependencies and build:

npm install && npm run build

Configure your MCP client:

{
  "mcpServers": {
    "browserbase": {
      "command": "node",
      "args": ["/path/to/mcp-server-browserbase/cli.js"],
      "env": {
        "BROWSERBASE_API_KEY": "",
        "BROWSERBASE_PROJECT_ID": "",
        "GEMINI_API_KEY": ""
      }
    }
  }
}

Docker Installation

Clone the repository:

git clone https://github.com/browserbase/mcp-server-browserbase.git
cd mcp-server-browserbase

Build the Docker image:

docker build -t mcp-browserbase .

Configure your MCP client:

{
  "mcpServers": {
    "browserbase": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "BROWSERBASE_API_KEY",
        "-e",
        "BROWSERBASE_PROJECT_ID",
        "-e",
        "GEMINI_API_KEY",
        "mcp-browserbase"
      ],
      "env": {
        "BROWSERBASE_API_KEY": "",
        "BROWSERBASE_PROJECT_ID": "",
        "GEMINI_API_KEY": ""
      }
    }
  }
}

Configuration Options

The Browserbase MCP server supports various configuration flags to customize its behavior:

Proxies

Enable Browserbase proxies:

{
  "mcpServers": {
    "browserbase": {
      "command": "npx",
      "args": ["@browserbasehq/mcp-server-browserbase", "--proxies"],
      "env": {
        "BROWSERBASE_API_KEY": "",
        "BROWSERBASE_PROJECT_ID": "",
        "GEMINI_API_KEY": ""
      }
    }
  }
}

Advanced Stealth

Enable advanced stealth features (Scale Plan Users only):

{
  "mcpServers": {
    "browserbase": {
      "command": "npx",
      "args": ["@browserbasehq/mcp-server-browserbase", "--advancedStealth"],
      "env": {
        "BROWSERBASE_API_KEY": "",
        "BROWSERBASE_PROJECT_ID": "",
        "GEMINI_API_KEY": ""
      }
    }
  }
}

Contexts

Use a specific Browserbase context:

{
  "mcpServers": {
    "browserbase": {
      "command": "npx",
      "args": [
        "@browserbasehq/mcp-server-browserbase",
        "--contextId",
        "<YOUR_CONTEXT_ID>"
      ],
      "env": {
        "BROWSERBASE_API_KEY": "",
        "BROWSERBASE_PROJECT_ID": "",
        "GEMINI_API_KEY": ""
      }
    }
  }
}

Browser Viewport Sizing

Customize the browser viewport dimensions:

{
  "mcpServers": {
    "browserbase": {
      "command": "npx",
      "args": [
        "@browserbasehq/mcp-server-browserbase",
        "--browserHeight",
        "1080",
        "--browserWidth",
        "1920"
      ],
      "env": {
        "BROWSERBASE_API_KEY": "",
        "BROWSERBASE_PROJECT_ID": "",
        "GEMINI_API_KEY": ""
      }
    }
  }
}

Experimental Features

Enable experimental features in Stagehand v3:

{
  "mcpServers": {
    "browserbase": {
      "command": "npx",
      "args": ["@browserbasehq/mcp-server-browserbase", "--experimental"],
      "env": {
        "BROWSERBASE_API_KEY": "",
        "BROWSERBASE_PROJECT_ID": "",
        "GEMINI_API_KEY": ""
      }
    }
  }
}

Custom Model Configuration

Use alternative models for Stagehand (requires model provider's API key):

{
  "mcpServers": {
    "browserbase": {
      "command": "npx",
      "args": [
        "@browserbasehq/mcp-server-browserbase",
        "--modelName",
        "anthropic/claude-sonnet-4.5",
        "--modelApiKey",
        "your-anthropic-api-key"
      ],
      "env": {
        "BROWSERBASE_API_KEY": "",
        "BROWSERBASE_PROJECT_ID": ""
      }
    }
  }
}

Available Features

The Browserbase MCP Server provides a comprehensive set of features:

Browser automation for navigating and interacting with web pages
Data extraction from web content
Form filling and interaction with web elements
Screenshot capture (full-page and element-specific)
Support for multiple AI models (OpenAI, Claude, Gemini, etc.)
Vision capabilities with annotated screenshots
Browser session management
High-performance operations with automatic caching
Advanced CSS selector support for precise element targeting

For more information about using MCP, visit the MCP Documentation or the Browserbase MCP Documentation.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "browserbase" '{"command":"npx","args":["-y","@browserbasehq/mcp-browserbase"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "browserbase": {
            "command": "npx",
            "args": [
                "-y",
                "@browserbasehq/mcp-browserbase"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "browserbase": {
            "command": "npx",
            "args": [
                "-y",
                "@browserbasehq/mcp-browserbase"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect